Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block

Pull core block layer updates from Jens Axboe:
 "This is the main pull request for block storage for 4.15-rc1.

  Nothing out of the ordinary in here, and no API changes or anything
  like that. Just various new features for drivers, core changes, etc.
  In particular, this pull request contains:

   - A patch series from Bart, closing the whole on blk/scsi-mq queue
     quescing.

   - A series from Christoph, building towards hidden gendisks (for
     multipath) and ability to move bio chains around.

   - NVMe
        - Support for native multipath for NVMe (Christoph).
        - Userspace notifications for AENs (Keith).
        - Command side-effects support (Keith).
        - SGL support (Chaitanya Kulkarni)
        - FC fixes and improvements (James Smart)
        - Lots of fixes and tweaks (Various)

   - bcache
        - New maintainer (Michael Lyle)
        - Writeback control improvements (Michael)
        - Various fixes (Coly, Elena, Eric, Liang, et al)

   - lightnvm updates, mostly centered around the pblk interface
     (Javier, Hans, and Rakesh).

   - Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)

   - Writeback series that fix the much discussed hundreds of millions
     of sync-all units. This goes all the way, as discussed previously
     (me).

   - Fix for missing wakeup on writeback timer adjustments (Yafang
     Shao).

   - Fix laptop mode on blk-mq (me).

   - {mq,name} tupple lookup for IO schedulers, allowing us to have
     alias names. This means you can use 'deadline' on both !mq and on
     mq (where it's called mq-deadline). (me).

   - blktrace race fix, oopsing on sg load (me).

   - blk-mq optimizations (me).

   - Obscure waitqueue race fix for kyber (Omar).

   - NBD fixes (Josef).

   - Disable writeback throttling by default on bfq, like we do on cfq
     (Luca Miccio).

   - Series from Ming that enable us to treat flush requests on blk-mq
     like any other request. This is a really nice cleanup.

   - Series from Ming that improves merging on blk-mq with schedulers,
     getting us closer to flipping the switch on scsi-mq again.

   - BFQ updates (Paolo).

   - blk-mq atomic flags memory ordering fixes (Peter Z).

   - Loop cgroup support (Shaohua).

   - Lots of minor fixes from lots of different folks, both for core and
     driver code"

* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
  nvme: fix visibility of "uuid" ns attribute
  blk-mq: fixup some comment typos and lengths
  ide: ide-atapi: fix compile error with defining macro DEBUG
  blk-mq: improve tag waiting setup for non-shared tags
  brd: remove unused brd_mutex
  blk-mq: only run the hardware queue if IO is pending
  block: avoid null pointer dereference on null disk
  fs: guard_bio_eod() needs to consider partitions
  xtensa/simdisk: fix compile error
  nvme: expose subsys attribute to sysfs
  nvme: create 'slaves' and 'holders' entries for hidden controllers
  block: create 'slaves' and 'holders' entries for hidden gendisks
  nvme: also expose the namespace identification sysfs files for mpath nodes
  nvme: implement multipath access to nvme subsystems
  nvme: track shared namespaces
  nvme: introduce a nvme_ns_ids structure
  nvme: track subsystems
  block, nvme: Introduce blk_mq_req_flags_t
  block, scsi: Make SCSI quiesce and resume work reliably
  block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
  ...

3 files changed, 132 insertions, 29 deletions

diff --git a/kernel/kthread.c b/kernel/kthread.c
index ba3992c..8af3130 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -20,7 +20,6 @@
 #include <linux/freezer.h>
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
-#include <linux/cgroup.h>
 #include <trace/events/sched.h>
 
 static DEFINE_SPINLOCK(kthread_create_lock);
@@ -47,6 +46,9 @@ struct kthread {
 	void *data;
 	struct completion parked;
 	struct completion exited;
+#ifdef CONFIG_BLK_CGROUP
+	struct cgroup_subsys_state *blkcg_css;
+#endif
 };
 
 enum KTHREAD_BITS {
@@ -74,11 +76,17 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 
 void free_kthread_struct(struct task_struct *k)
 {
+	struct kthread *kthread;
+
 	/*
 	 * Can be NULL if this kthread was created by kernel_thread()
 	 * or if kmalloc() in kthread() failed.
 	 */
-	kfree(to_kthread(k));
+	kthread = to_kthread(k);
+#ifdef CONFIG_BLK_CGROUP
+	WARN_ON_ONCE(kthread && kthread->blkcg_css);
+#endif
+	kfree(kthread);
 }
 
 /**
@@ -196,7 +204,7 @@ static int kthread(void *_create)
 	struct kthread *self;
 	int ret;
 
-	self = kmalloc(sizeof(*self), GFP_KERNEL);
+	self = kzalloc(sizeof(*self), GFP_KERNEL);
 	set_kthread_struct(self);
 
 	/* If user was SIGKILLed, I release the structure. */
@@ -212,7 +220,6 @@ static int kthread(void *_create)
 		do_exit(-ENOMEM);
 	}
 
-	self->flags = 0;
 	self->data = data;
 	init_completion(&self->exited);
 	init_completion(&self->parked);
@@ -1152,3 +1159,54 @@ void kthread_destroy_worker(struct kthread_worker *worker)
 	kfree(worker);
 }
 EXPORT_SYMBOL(kthread_destroy_worker);
+
+#ifdef CONFIG_BLK_CGROUP
+/**
+ * kthread_associate_blkcg - associate blkcg to current kthread
+ * @css: the cgroup info
+ *
+ * Current thread must be a kthread. The thread is running jobs on behalf of
+ * other threads. In some cases, we expect the jobs attach cgroup info of
+ * original threads instead of that of current thread. This function stores
+ * original thread's cgroup info in current kthread context for later
+ * retrieval.
+ */
+void kthread_associate_blkcg(struct cgroup_subsys_state *css)
+{
+	struct kthread *kthread;
+
+	if (!(current->flags & PF_KTHREAD))
+		return;
+	kthread = to_kthread(current);
+	if (!kthread)
+		return;
+
+	if (kthread->blkcg_css) {
+		css_put(kthread->blkcg_css);
+		kthread->blkcg_css = NULL;
+	}
+	if (css) {
+		css_get(css);
+		kthread->blkcg_css = css;
+	}
+}
+EXPORT_SYMBOL(kthread_associate_blkcg);
+
+/**
+ * kthread_blkcg - get associated blkcg css of current kthread
+ *
+ * Current thread must be a kthread.
+ */
+struct cgroup_subsys_state *kthread_blkcg(void)
+{
+	struct kthread *kthread;
+
+	if (current->flags & PF_KTHREAD) {
+		kthread = to_kthread(current);
+		if (kthread)
+			return kthread->blkcg_css;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(kthread_blkcg);
+#endif
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d9c31bc..9576bd5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1342,11 +1342,6 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &zero,
 	},
 	{
-		.procname       = "nr_pdflush_threads",
-		.mode           = 0444 /* read-only */,
-		.proc_handler   = pdflush_proc_obsolete,
-	},
-	{
 		.procname	= "swappiness",
 		.data		= &vm_swappiness,
 		.maxlen		= sizeof(vm_swappiness),
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 45a3928..206e0e2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -66,7 +66,8 @@ static struct tracer_flags blk_tracer_flags = {
 };
 
 /* Global reference count of probes */
-static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+static DEFINE_MUTEX(blk_probe_mutex);
+static int blk_probes_ref;
 
 static void blk_register_tracepoints(void);
 static void blk_unregister_tracepoints(void);
@@ -329,14 +330,29 @@ static void blk_trace_free(struct blk_trace *bt)
 	kfree(bt);
 }
 
+static void get_probe_ref(void)
+{
+	mutex_lock(&blk_probe_mutex);
+	if (++blk_probes_ref == 1)
+		blk_register_tracepoints();
+	mutex_unlock(&blk_probe_mutex);
+}
+
+static void put_probe_ref(void)
+{
+	mutex_lock(&blk_probe_mutex);
+	if (!--blk_probes_ref)
+		blk_unregister_tracepoints();
+	mutex_unlock(&blk_probe_mutex);
+}
+
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
 	blk_trace_free(bt);
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
+	put_probe_ref();
 }
 
-int blk_trace_remove(struct request_queue *q)
+static int __blk_trace_remove(struct request_queue *q)
 {
 	struct blk_trace *bt;
 
@@ -349,6 +365,17 @@ int blk_trace_remove(struct request_queue *q)
 
 	return 0;
 }
+
+int blk_trace_remove(struct request_queue *q)
+{
+	int ret;
+
+	mutex_lock(&q->blk_trace_mutex);
+	ret = __blk_trace_remove(q);
+	mutex_unlock(&q->blk_trace_mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(blk_trace_remove);
 
 static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
@@ -538,8 +565,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto err;
 
-	if (atomic_inc_return(&blk_probes_ref) == 1)
-		blk_register_tracepoints();
+	get_probe_ref();
 
 	ret = 0;
 err:
@@ -550,9 +576,8 @@ err:
 	return ret;
 }
 
-int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-		    struct block_device *bdev,
-		    char __user *arg)
+static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			     struct block_device *bdev, char __user *arg)
 {
 	struct blk_user_trace_setup buts;
 	int ret;
@@ -571,6 +596,19 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	}
 	return 0;
 }
+
+int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+		    struct block_device *bdev,
+		    char __user *arg)
+{
+	int ret;
+
+	mutex_lock(&q->blk_trace_mutex);
+	ret = __blk_trace_setup(q, name, dev, bdev, arg);
+	mutex_unlock(&q->blk_trace_mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(blk_trace_setup);
 
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
@@ -607,7 +645,7 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 }
 #endif
 
-int blk_trace_startstop(struct request_queue *q, int start)
+static int __blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
 	struct blk_trace *bt = q->blk_trace;
@@ -646,6 +684,17 @@ int blk_trace_startstop(struct request_queue *q, int start)
 
 	return ret;
 }
+
+int blk_trace_startstop(struct request_queue *q, int start)
+{
+	int ret;
+
+	mutex_lock(&q->blk_trace_mutex);
+	ret = __blk_trace_startstop(q, start);
+	mutex_unlock(&q->blk_trace_mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(blk_trace_startstop);
 
 /*
@@ -676,7 +725,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	switch (cmd) {
 	case BLKTRACESETUP:
 		bdevname(bdev, b);
-		ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
+		ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
 	case BLKTRACESETUP32:
@@ -687,10 +736,10 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	case BLKTRACESTART:
 		start = 1;
 	case BLKTRACESTOP:
-		ret = blk_trace_startstop(q, start);
+		ret = __blk_trace_startstop(q, start);
 		break;
 	case BLKTRACETEARDOWN:
-		ret = blk_trace_remove(q);
+		ret = __blk_trace_remove(q);
 		break;
 	default:
 		ret = -ENOTTY;
@@ -708,10 +757,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
+	mutex_lock(&q->blk_trace_mutex);
+
 	if (q->blk_trace) {
-		blk_trace_startstop(q, 0);
-		blk_trace_remove(q);
+		__blk_trace_startstop(q, 0);
+		__blk_trace_remove(q);
 	}
+
+	mutex_unlock(&q->blk_trace_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1558,9 +1611,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
-
+	put_probe_ref();
 	blk_trace_free(bt);
 	return 0;
 }
@@ -1591,8 +1642,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
 	if (cmpxchg(&q->blk_trace, NULL, bt))
 		goto free_bt;
 
-	if (atomic_inc_return(&blk_probes_ref) == 1)
-		blk_register_tracepoints();
+	get_probe_ref();
 	return 0;
 
 free_bt: